
import pandas as pd
df = pd.read_excel('BDMAESTRIA_ORIGINAL.xlsx')
df.head(1)


import numpy as np
for col in df:
    if df[col].dtype==np.object:
        df[col] = df[col].fillna('None') # llenar los espacios en blanco con ninguno/None
    else:
        df[col] = df[col].fillna(0)  # las variables de tipo distinto de object llenar con ceros


secuencia = df['Secuencia'] == 1.0
df=df[secuencia]
df= df.drop(['Secuencia'], axis=1)
df.reset_index(drop=True, inplace=True)


#Variable Dummy Marcas
for i in range(0,len(df)):
    if df.iloc[i,3] != 'RENAULT' and df.iloc[i,3] != 'MAZDA' and df.iloc[i,3] != 'CHEVROLET' and df.iloc[i,3] != 'TOYOTA' and df.iloc[i,3] != 'HYUNDAI':
        df.iloc[i,3] = 'OTRA'     
print(df.shape)
df.head(1)

(9226, 25)


from dataprep.eda import create_report
report = create_report(df)
report


from dataprep.eda import plot
plot(df, "Codigo resultado","Nivel de contaminacion")


from dataprep.eda import plot
plot(df, "Marca","Nivel de contaminacion")


plot(df, "Linea","Nivel de contaminacion")


plot(df, "Modelo","Nivel de contaminacion")


plot(df, "Combustible","Nivel de contaminacion")


plot(df, "Cilindraje","Nivel de contaminacion")


plot(df, "Kilometraje","Nivel de contaminacion")


plot(df, "Gases  temperatura ambiente","Nivel de contaminacion")


plot(df, "Gases  humedad relativa","Nivel de contaminacion")


for i in range(0,len(df)):
    
    if df.iloc[i,3] == 'RENAULT':
        df.iloc[i,3] = 1
    elif df.iloc[i,3] == 'MAZDA':
        df.iloc[i,3] = 2
    elif df.iloc[i,3] == 'CHEVROLET':
        df.iloc[i,3] = 3
    elif df.iloc[i,3] == 'TOYOTA':
        df.iloc[i,3] = 4
    elif df.iloc[i,3] == 'HYUNDAI':
        df.iloc[i,3] = 5
    elif df.iloc[i,3] == 'OTRA':
        df.iloc[i,3] =6
df['Marca']=pd.to_numeric(df['Marca'])


for i in range(0,len(df)):    
    if df.iloc[i,7] == 'GAS - GASOLINA':
        df.iloc[i,7] = 1
    elif df.iloc[i,7] == 'GAS NATURAL VEHICULAR':
        df.iloc[i,7] = 2
    elif df.iloc[i,7] == 'GASOLINA':
        df.iloc[i,7] = 3
    elif df.iloc[i,7] == 'GASOLINA - ELECTRICO':
        df.iloc[i,7] = 4
df['Combustible']=pd.to_numeric(df['Combustible'])


print(list(df.columns))

['Numero fur', 'Fecha inicio', 'Codigo resultado', 'Marca', 'Linea', 'Modelo', 'Fecha matricula', 'Combustible', 'Cilindraje', 'Kilometraje', 'Gases  temperatura ambiente', 'Gases  humedad relativa', 'Gases  convertidor catalitico', 'Gases  ralenti  rpm', 'Gases  ralenti  co', 'Gases  ralenti  hc', 'Gases  ralenti  co2', 'Gases  ralenti  o2', 'Gases  crucero  rpm', 'Gases  crucero  co', 'Gases  crucero  hc', 'Gases  crucero  co2', 'Gases  crucero  o2', 'Nivel de contaminacion', 'Clasificacion nivel de contaminacion']


# definir variables:
X = df[['Codigo resultado', 'Marca','Modelo','Combustible','Gases  ralenti  co', 'Gases  ralenti  hc', 'Gases  ralenti  co2', 'Gases  ralenti  o2', 'Gases  crucero  co', 'Gases  crucero  hc', 
        'Gases  crucero  co2', 'Gases  crucero  o2', 'Nivel de contaminacion', 'Clasificacion nivel de contaminacion']]
X.dtypes

Codigo resultado                          int64
Marca                                     int64
Modelo                                    int64
Combustible                               int64
Gases  ralenti  co                      float64
Gases  ralenti  hc                      float64
Gases  ralenti  co2                     float64
Gases  ralenti  o2                      float64
Gases  crucero  co                      float64
Gases  crucero  hc                      float64
Gases  crucero  co2                     float64
Gases  crucero  o2                      float64
Nivel de contaminacion                  float64
Clasificacion nivel de contaminacion      int64
dtype: object


X_centralizada = X - X.mean()


X_correlacion = np.corrcoef(X_centralizada,rowvar=False)# Crear matriz de correlación forma 1


from dataprep.eda import plot_correlation
plot_correlation(X_centralizada)


matriz_cov = np.cov(X_centralizada, rowvar=False)


determinante = np.linalg.det(matriz_cov) 
determinante

280042.1585151153


ncondicion = np.linalg.cond(matriz_cov) 
ncondicion

439713670.9496324


from sklearn.covariance import LedoitWolf
cov_LW = LedoitWolf().fit(X_centralizada)
cov_LW_encogida = cov_LW.covariance_


cov_LW_shrinkage = cov_LW.shrinkage_
cov_LW_shrinkage

0.04384637018486556


determinante_LW = np.linalg.det(cov_LW_encogida) 
determinante_LW

3.329682881740641e+46


ncondicion_LW = np.linalg.cond(cov_LW_encogida) 
ncondicion_LW

257.15176313170514


X_centralizada = X_centralizada.values
Número_filas, Número_columnas=X_centralizada.shape

Transpuesta=X_centralizada.transpose()
cov_LW_encogida=cov_LW_encogida
Inverso_covarianza=np.linalg.inv(cov_LW_encogida)
MD=np.zeros((Número_filas, 1))

for i in range(1,Número_filas):
    tem1=np.dot(X_centralizada[i,:],Inverso_covarianza)
    tem2=np.dot(tem1,Transpuesta[:,i])
    MD[i]=np.sqrt(tem2)

print('La distancia de Mahalanobis es: \n', MD)

La distancia de Mahalanobis es: 
 [[ 0.        ]
 [ 0.56631968]
 [ 0.46561107]
 ...
 [39.20725525]
 [27.71327871]
 [35.12280348]]


MD = pd.DataFrame(MD)
MD.columns = ['Distancias_Mahal']


corte = np.percentile(MD, 99.99)
corte

38.46324038107876


X_99 = []
X_99 = pd.concat([X,MD],axis=1)
X_99_corte = X_99['Distancias_Mahal'] < corte
X_99 = X_99[X_99_corte]
X_99.reset_index(drop=True, inplace=True)
X_99 = X_99.drop(['Distancias_Mahal'],axis=1)
X_99.head(2)


plot(X_99)


cov_LW99 = LedoitWolf().fit(X_99)
cov_LW99_encogida = cov_LW.covariance_


autovalor,autovector = np.linalg.eig(cov_LW99_encogida)


autovalor.round(3)

array([273441.706,  53221.611,   1149.258,   1068.475,   1066.801,
         1066.473,   1063.986,   1064.053,   1063.605,   1063.57 ,
         1063.495,   1063.397,   1063.365,   1063.348])


autovector.round(3)

array([[ 0.   ,  0.   ,  0.008, -0.072, -0.007,  0.   , -0.029, -0.002,
        -0.341,  0.225,  0.909, -0.002,  0.009, -0.   ],
       [-0.   , -0.   ,  0.004,  0.076,  0.363,  0.929, -0.007, -0.01 ,
        -0.013,  0.004,  0.002,  0.007, -0.   ,  0.   ],
       [-0.006,  0.001, -0.988, -0.148, -0.041,  0.032, -0.007, -0.008,
        -0.002, -0.001, -0.004, -0.001, -0.001, -0.   ],
       [-0.   , -0.   , -0.003,  0.004,  0.029, -0.019,  0.001,  0.043,
        -0.175, -0.222, -0.008,  0.957, -0.03 ,  0.003],
       [ 0.001, -0.   ,  0.053, -0.466,  0.278, -0.067,  0.614, -0.189,
        -0.066, -0.261,  0.021, -0.061,  0.334, -0.312],
       [ 0.817, -0.577, -0.006,  0.004,  0.   , -0.   , -0.001, -0.   ,
         0.   ,  0.001, -0.   ,  0.   , -0.   , -0.006],
       [-0.002,  0.   , -0.07 ,  0.38 ,  0.31 , -0.158, -0.382, -0.134,
        -0.341, -0.375, -0.02 , -0.141,  0.536,  0.047],
       [ 0.001, -0.   ,  0.048, -0.108, -0.645,  0.266, -0.002,  0.502,
        -0.134, -0.274,  0.001, -0.074,  0.37 , -0.104],
       [ 0.001,  0.   ,  0.065, -0.514,  0.278, -0.066, -0.549,  0.283,
        -0.015, -0.255,  0.004, -0.09 , -0.312, -0.313],
       [ 0.577,  0.817, -0.003,  0.004,  0.   , -0.   ,  0.001,  0.001,
         0.001,  0.001,  0.   ,  0.   , -0.   , -0.006],
       [-0.001, -0.001, -0.068,  0.359,  0.155, -0.084,  0.408,  0.396,
        -0.323, -0.356,  0.016, -0.184, -0.495,  0.044],
       [ 0.001,  0.001,  0.036, -0.035, -0.415,  0.156, -0.088, -0.674,
        -0.249, -0.367, -0.01 , -0.095, -0.348, -0.107],
       [ 0.01 ,  0.002,  0.059, -0.402,  0.046,  0.016,  0.011, -0.002,
        -0.04 , -0.22 ,  0.008, -0.06 ,  0.006,  0.882],
       [ 0.001,  0.   ,  0.032, -0.196,  0.004,  0.003, -0.003,  0.028,
        -0.739,  0.491, -0.414, -0.025, -0.001, -0.   ]])


#Proporción de los autovalores:
proporcion=autovalor/sum(autovalor)
proporcion

array([0.80536985, 0.156754  , 0.00338492, 0.00314699, 0.00314206,
       0.00314109, 0.00313377, 0.00313396, 0.00313264, 0.00313254,
       0.00313232, 0.00313203, 0.00313194, 0.00313189])


0.80532972 + 0.15696405 # 96% de la variabilidad de los datos en 2 dimensiones

0.96229377


#Se procede a extraer la columna 1 ya que es el vector de proyección de la máxima sombra, así:
vector_proyeccion=autovector[:,1]


# Forma 2 PCA
from sklearn.decomposition import PCA

# Instanciar número de componentes
n_componentes = 13 # intuición
pca = PCA(n_components = n_componentes)
pca

PCA(n_components=13)


X_PCA = pca.fit_transform(cov_LW_encogida) 
X_PCA = pd.DataFrame(X_PCA)


pca.explained_variance_ratio_

array([9.57828713e-01, 4.19829520e-02, 1.95114605e-05, 1.69907148e-05,
       1.69509941e-05, 1.69299280e-05, 1.68644161e-05, 1.68624063e-05,
       1.68495594e-05, 1.68469367e-05, 1.68437831e-05, 1.68427289e-05,
       1.68421797e-05])


sum(pca.explained_variance_ratio_)

1.0000000000000002


sum(pca.explained_variance_ratio_[:1])

0.9578287128465874


X_99.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9225 entries, 0 to 9224
Data columns (total 14 columns):
 #   Column                                Non-Null Count  Dtype  
---  ------                                --------------  -----  
 0   Codigo resultado                      9225 non-null   int64  
 1   Marca                                 9225 non-null   int64  
 2   Modelo                                9225 non-null   int64  
 3   Combustible                           9225 non-null   int64  
 4   Gases  ralenti  co                    9225 non-null   float64
 5   Gases  ralenti  hc                    9225 non-null   float64
 6   Gases  ralenti  co2                   9225 non-null   float64
 7   Gases  ralenti  o2                    9225 non-null   float64
 8   Gases  crucero  co                    9225 non-null   float64
 9   Gases  crucero  hc                    9225 non-null   float64
 10  Gases  crucero  co2                   9225 non-null   float64
 11  Gases  crucero  o2                    9225 non-null   float64
 12  Nivel de contaminacion                9225 non-null   float64
 13  Clasificacion nivel de contaminacion  9225 non-null   int64  
dtypes: float64(9), int64(5)
memory usage: 1009.1 KB


X = X_99[[ 'Marca','Modelo','Combustible','Gases  ralenti  co', 'Gases  ralenti  hc', 'Gases  ralenti  co2', 'Gases  ralenti  o2', 'Gases  crucero  co', 'Gases  crucero  hc', 
        'Gases  crucero  co2', 'Gases  crucero  o2']]


y = X_99[['Clasificacion nivel de contaminacion']]


print(X.shape, y.shape)

(9225, 11) (9225, 1)


from sklearn.model_selection import train_test_split
# separar los datos en train y eval
x_train, x_eval, y_train, y_eval = train_test_split(X, y, test_size=0.20, train_size=0.80, random_state=0)


import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
import matplotlib.patches as mpatches

import seaborn as sb
plt.rcParams['figure.figsize'] = (16, 9)
plt.style.use('ggplot')


from sklearn.preprocessing import MinMaxScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix


scaler = MinMaxScaler() #para normalizar
x_train = scaler.fit_transform(x_train)
x_eval = scaler.transform(x_eval)


import warnings
warnings.filterwarnings('ignore')
from matplotlib import style


k_range = range(1, 30)
scores = []
for k in k_range:
    knn = KNeighborsClassifier(n_neighbors = k)
    knn.fit(x_train, y_train)
    scores.append(knn.score(x_eval, y_eval))

plt.figure()
fig, ax = plt.subplots(figsize=(6, 3.84));
plt.xlabel('k')
plt.ylabel('accuracy')
plt.scatter(k_range, scores)
plt.xticks([0,5,10,15,30]);

<Figure size 1152x648 with 0 Axes>


n_neighbors = 7

knn = KNeighborsClassifier(n_neighbors)
knn.fit(x_train, y_train)
print('Precisión del clasificador K-NN en el conjunto de entrenamiento: {:.2f}'
     .format(knn.score(x_train, y_train)))
print('Precisión del clasificador K-NN en el conjunto de prueba: {:.2f}'
     .format(knn.score(x_eval, y_eval)))

Precisión del clasificador K-NN en el conjunto de entrenamiento: 0.85
Precisión del clasificador K-NN en el conjunto de prueba: 0.83


pred = knn.predict(x_eval)
print('\n')
print(confusion_matrix(y_eval, pred))
print('\n')
print(classification_report(y_eval, pred))


[[ 172   70    0    0    0]
 [  86 1237    5    5    1]
 [   0   57   17   10    2]
 [   0   33   15   49   10]
 [   0   15    3    8   50]]


              precision    recall  f1-score   support

           1       0.67      0.71      0.69       242
           2       0.88      0.93      0.90      1334
           3       0.42      0.20      0.27        86
           4       0.68      0.46      0.55       107
           5       0.79      0.66      0.72        76

    accuracy                           0.83      1845
   macro avg       0.69      0.59      0.63      1845
weighted avg       0.81      0.83      0.82      1845


confusion_matrixV = confusion_matrix(y_eval, pred)
confusion_matrixV = pd.DataFrame(confusion_matrixV)

verdaderos_positivos = np.diag(confusion_matrixV)
falsos_positivos = confusion_matrixV.sum(axis=0) - verdaderos_positivos
falsos_negativos = confusion_matrixV.sum(axis=1) - verdaderos_positivos
verdaderos_negativos = (confusion_matrixV.to_numpy().sum() - (verdaderos_positivos + falsos_positivos + falsos_negativos))

confusion_matrixV.columns = ['Nivel 1','Nivel 2','Nivel 3','Nivel 4','Nivel 5']

for dato, vp, fp, vn, fn in zip(
    confusion_matrixV.columns,
    verdaderos_positivos, falsos_positivos,
    verdaderos_negativos, falsos_negativos):

    frame = pd.DataFrame.from_dict(
        {"Positive(1)": (vp, fp), "Negative(0)": (fn, vn)},
        orient="Index",
        columns=("Positive(1)", "Negative(0)"))
    
    frame.index.name = f'Predicted Values for "{dato}"'
    frame.columns.name = f'Actual values for "{dato}"'
    print(frame, "\n")

Actual values for "Nivel 1"     Positive(1)  Negative(0)
Predicted Values for "Nivel 1"                          
Positive(1)                             172           86
Negative(0)                              70         1517 

Actual values for "Nivel 2"     Positive(1)  Negative(0)
Predicted Values for "Nivel 2"                          
Positive(1)                            1237          175
Negative(0)                              97          336 

Actual values for "Nivel 3"     Positive(1)  Negative(0)
Predicted Values for "Nivel 3"                          
Positive(1)                              17           23
Negative(0)                              69         1736 

Actual values for "Nivel 4"     Positive(1)  Negative(0)
Predicted Values for "Nivel 4"                          
Positive(1)                              49           23
Negative(0)                              58         1715 

Actual values for "Nivel 5"     Positive(1)  Negative(0)
Predicted Values for "Nivel 5"                          
Positive(1)                              50           13
Negative(0)                              26         1756


X = X_99[[ 'Marca','Modelo','Combustible','Gases  ralenti  co', 'Gases  ralenti  hc', 'Gases  ralenti  co2', 'Gases  ralenti  o2', 'Gases  crucero  co', 'Gases  crucero  hc', 
        'Gases  crucero  co2', 'Gases  crucero  o2']]


y = X_99[['Clasificacion nivel de contaminacion']]


print(X.shape, y.shape)

(9225, 11) (9225, 1)


from sklearn.model_selection import train_test_split
# separar los datos en train y eval
x_train, x_eval, y_train, y_eval = train_test_split(X, y, test_size=0.20, train_size=0.80, random_state=0)


from sklearn.tree import DecisionTreeClassifier
# creando el modelo sin control de profundidad, crecerá hasta que todas las hojas sean puras
arbol = DecisionTreeClassifier(criterion = 'gini')
# ajustando el modelo
arbol.fit(x_train, y_train)

DecisionTreeClassifier()


from sklearn.tree import export_graphviz
from graphviz import Source 
import os
# estructura del árbol creado en el paso anterior:
print(f"Profundidad del árbol: {arbol.get_depth()}")
print(f"Número de nodos terminales: {arbol.get_n_leaves()}")

Profundidad del árbol: 17
Número de nodos terminales: 345


# precisión del modelo en datos de entrenamiento.
print("precisión entranamiento: {0: .2f}".format(
        arbol.score(x_train, y_train)))

precisión entranamiento:  1.00


# precisión del modelo en datos de evaluación.
print("precisión evaluación: {0: .2f}".format(arbol.score(x_eval, y_eval)))

precisión evaluación:  0.93


# profundidad del arbol de decisión
arbol.tree_.max_depth

17


import matplotlib.pyplot as plt
# Gráfico de ajuste del árbol de decisión
#fig, ax = plt.subplots(figsize=(10, 5))
fig, ax = plt.subplots(figsize=(6, 3.84));
train_prec =  []
eval_prec = []
max_deep_list = list(range(1,30))

for deep in max_deep_list:
    arbol3 = DecisionTreeClassifier(criterion='gini', max_depth=deep)
    arbol3.fit(x_train, y_train)
    train_prec.append(arbol3.score(x_train, y_train))
    eval_prec.append(arbol3.score(x_eval, y_eval))

# graficar los resultados.
plt.plot(max_deep_list, train_prec, color='r', label='entrenamiento')
plt.plot(max_deep_list, eval_prec, color='b', label='evaluación')
plt.title('Gráfico de ajuste árbol de decisión')
plt.legend()
plt.ylabel('precisión')
plt.xlabel('profundidad del árbol / complejidad')
plt.show()


# modelo dos, con control de profundidad
arbol2 = DecisionTreeClassifier(criterion='gini', max_depth=4)

# Ajustando el modelo
arbol2.fit(x_train, y_train)

DecisionTreeClassifier(max_depth=4)


from sklearn.tree import plot_tree
import pydotplus
# Estructura del árbol creado
# ------------------------------------------------------------------------------
fig, ax = plt.subplots(figsize=(30, 5))

print(f"Profundidad del árbol: {arbol2.get_depth()}")
print(f"Número de nodos terminales: {arbol2.get_n_leaves()}")

plot = plot_tree(
            decision_tree = arbol2,
            feature_names = X.columns,
            class_names   = ['Nivel 1','Nivel 2','Nivel 3','Nivel 4','Nivel 5'],
            filled        = True,
            impurity      = False,
            fontsize      = 8,
            ax            = ax
       )

Profundidad del árbol: 4
Número de nodos terminales: 16


# guardar png del árbol2:
import pydotplus

print(f"Profundidad del árbol: {arbol2.get_depth()}")
print(f"Número de nodos terminales: {arbol2.get_n_leaves()}")
labels = list(X.columns)
data = export_graphviz(decision_tree = arbol2,
                       feature_names = X.columns,
                       class_names   = ['Nivel 1','Nivel 2','Nivel 3','Nivel 4','Nivel 5'],
                       rounded       = True,
                       filled        = True)   
graph = pydotplus.graph_from_dot_data(data)
graph.write_png('Árbol_decisión_CDA.png')

Profundidad del árbol: 4
Número de nodos terminales: 16

True


from sklearn.tree import export_text
texto_modelo = export_text(decision_tree = arbol2, feature_names = list(X.columns))
print(texto_modelo)

|--- Gases  ralenti  hc <= 349.50
|   |--- Gases  ralenti  hc <= 17.50
|   |   |--- Gases  ralenti  o2 <= 0.44
|   |   |   |--- Gases  crucero  hc <= 18.50
|   |   |   |   |--- class: 1
|   |   |   |--- Gases  crucero  hc >  18.50
|   |   |   |   |--- class: 2
|   |   |--- Gases  ralenti  o2 >  0.44
|   |   |   |--- Gases  ralenti  o2 <= 0.81
|   |   |   |   |--- class: 2
|   |   |   |--- Gases  ralenti  o2 >  0.81
|   |   |   |   |--- class: 2
|   |--- Gases  ralenti  hc >  17.50
|   |   |--- Gases  crucero  hc <= 221.50
|   |   |   |--- Gases  crucero  co <= 2.30
|   |   |   |   |--- class: 2
|   |   |   |--- Gases  crucero  co >  2.30
|   |   |   |   |--- class: 2
|   |   |--- Gases  crucero  hc >  221.50
|   |   |   |--- Gases  crucero  co2 <= 11.65
|   |   |   |   |--- class: 4
|   |   |   |--- Gases  crucero  co2 >  11.65
|   |   |   |   |--- class: 3
|--- Gases  ralenti  hc >  349.50
|   |--- Gases  crucero  co2 <= 11.75
|   |   |--- Gases  ralenti  hc <= 533.00
|   |   |   |--- Gases  ralenti  co <= 5.76
|   |   |   |   |--- class: 4
|   |   |   |--- Gases  ralenti  co >  5.76
|   |   |   |   |--- class: 5
|   |   |--- Gases  ralenti  hc >  533.00
|   |   |   |--- Gases  crucero  hc <= 192.50
|   |   |   |   |--- class: 5
|   |   |   |--- Gases  crucero  hc >  192.50
|   |   |   |   |--- class: 5
|   |--- Gases  crucero  co2 >  11.75
|   |   |--- Gases  ralenti  hc <= 469.00
|   |   |   |--- Gases  crucero  hc <= 286.00
|   |   |   |   |--- class: 3
|   |   |   |--- Gases  crucero  hc >  286.00
|   |   |   |   |--- class: 4
|   |   |--- Gases  ralenti  hc >  469.00
|   |   |   |--- Gases  ralenti  hc <= 1078.00
|   |   |   |   |--- class: 4
|   |   |   |--- Gases  ralenti  hc >  1078.00
|   |   |   |   |--- class: 5


# precisión del modelo en datos de entrenamiento.
print("precisión entrenamiento: {0: .2f}".format(
        arbol2.score(x_train, y_train)))

precisión entrenamiento:  0.89


# precisión del modelo en datos de evaluación.
print("precisión evaluación: {0: .2f}".format(
        arbol2.score(x_eval, y_eval)))

precisión evaluación:  0.88


y_pred = arbol2.predict(x_eval)
print(confusion_matrix(y_eval, y_pred))

[[ 172   70    0    0    0]
 [  15 1288   30    1    0]
 [   0   28   43   15    0]
 [   0   16   14   70    7]
 [   0    0    1   17   58]]


matriz_confusion = confusion_matrix(y_eval, y_pred)
matriz_confusion = pd.DataFrame(matriz_confusion)

verdaderos_positivos = np.diag(matriz_confusion)
falsos_positivos = matriz_confusion.sum(axis=0) - verdaderos_positivos
falsos_negativos = matriz_confusion.sum(axis=1) - verdaderos_positivos
verdaderos_negativos = (matriz_confusion.to_numpy().sum() - (verdaderos_positivos + falsos_positivos + falsos_negativos))

matriz_confusion.columns = ['Nivel 1','Nivel 2','Nivel 3','Nivel 4','Nivel 5']

for dato, vp, fp, vn, fn in zip(
    matriz_confusion.columns,
    verdaderos_positivos, falsos_positivos,
    verdaderos_negativos, falsos_negativos):

    frame = pd.DataFrame.from_dict(
        {"Positive(1)": (vp, fp), "Negative(0)": (fn, vn)},
        orient="Index",
        columns=("Positive(1)", "Negative(0)"))
    
    frame.index.name = f'Predicted Values for "{dato}"'
    frame.columns.name = f'Actual values for "{dato}"'
    print(frame, "\n")

Actual values for "Nivel 1"     Positive(1)  Negative(0)
Predicted Values for "Nivel 1"                          
Positive(1)                             172           15
Negative(0)                              70         1588 

Actual values for "Nivel 2"     Positive(1)  Negative(0)
Predicted Values for "Nivel 2"                          
Positive(1)                            1288          114
Negative(0)                              46          397 

Actual values for "Nivel 3"     Positive(1)  Negative(0)
Predicted Values for "Nivel 3"                          
Positive(1)                              43           45
Negative(0)                              43         1714 

Actual values for "Nivel 4"     Positive(1)  Negative(0)
Predicted Values for "Nivel 4"                          
Positive(1)                              70           33
Negative(0)                              37         1705 

Actual values for "Nivel 5"     Positive(1)  Negative(0)
Predicted Values for "Nivel 5"                          
Positive(1)                              58            7
Negative(0)                              18         1762


from sklearn.metrics import classification_report
print(classification_report(y_eval, y_pred));

              precision    recall  f1-score   support

           1       0.92      0.71      0.80       242
           2       0.92      0.97      0.94      1334
           3       0.49      0.50      0.49        86
           4       0.68      0.65      0.67       107
           5       0.89      0.76      0.82        76

    accuracy                           0.88      1845
   macro avg       0.78      0.72      0.75      1845
weighted avg       0.88      0.88      0.88      1845


# Curvas de aprendizaje
from sklearn.model_selection import learning_curve

train_sizes, train_scores, test_scores = learning_curve(estimator=arbol, X=x_train, y=y_train, 
                                                        train_sizes=np.linspace(0.1, 1.0, 10), 
                                                        n_jobs=-1)
train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)


# graficando las curvas
#fig, ax = plt.subplots(figsize=(10, 5))
fig, ax = plt.subplots(figsize=(6, 3.84));
plt.plot(train_sizes, train_mean, color='r', marker='o', markersize=5,
         label='entrenamiento')
plt.fill_between(train_sizes, train_mean + train_std, 
                 train_mean - train_std, alpha=0.15, color='r')
plt.plot(train_sizes, test_mean, color='b', linestyle='--', 
         marker='s', markersize=5, label='evaluacion')
plt.fill_between(train_sizes, test_mean + test_std, 
                 test_mean - test_std, alpha=0.15, color='b')
plt.grid()
plt.title('Curva de aprendizaje')
plt.legend(loc='best')
plt.xlabel('Tamaño')
plt.ylabel('Precisión')
plt.show()


# Gráfico de importancia de los predictores en los modelos: arbol y arbol2
import matplotlib.pyplot as plt
from matplotlib import style
import seaborn as sns
style.use('ggplot') or plt.style.use('ggplot')

# visualizar importancia con el modelo 'arbol':
fig, ax = plt.subplots(figsize=(20, 6))
plt.subplot(2, 1, 1)
x = X.columns
y1 = arbol.feature_importances_ #importancia de cada variable predictora
sns.barplot(x=x, y=y1)
plt.title('Importancia de cada Predictor con el modelo: "arbol"')

# visualizar importancia con el modelo 'arbol2':
fig, ax = plt.subplots(figsize=(20, 6))
plt.subplot(2, 1, 2)
y2 = arbol2.feature_importances_ #importancia de cada variable predictora
sns.barplot(x=x, y=y2)
plt.title('Importancia de cada Predictor con el modelo: "arbol2"')
plt.show()


# predictores del modelo "arbol" vs arbol2" en orden de importancia:
importancia = pd.DataFrame({'Predictor':list(X.columns),'Importancia_arbol':np.round(arbol.feature_importances_,3),'Importancia_arbol2':np.round(arbol2.feature_importances_,3)})
importancia = importancia.sort_values('Importancia_arbol2',ascending=False)
importancia


from mlxtend.plotting import plot_decision_regions
# regiones de decisión en 2D con las variables más representativas del modelo final ("arbol2"):
X= pd.concat([X_99['Gases  ralenti  hc'],X_99['Gases  ralenti  o2']], axis=1)
y = X_99['Clasificacion nivel de contaminacion']

X2 = X.iloc[:,[1,0]].values # variable 1 = Gases ralenti hc ; variable 3 = Gases ralenti o2
y2 = y.iloc[:].values       # variable respuesta = Clasificacion nivel de contaminacion
arbol2.fit(X2,y2)           # usamos el arbol2 resultante en el modelo final
fig, ax = plt.subplots(figsize=(10, 7))
plot_decision_regions(X2, y2, clf=arbol2, legend=2)
plt.xlabel('Gases  ralenti  hc')
plt.ylabel('Gases  ralenti  o2')
plt.title('Clasificación de gases hc y o2 con respecto al nivel de contaminación')
plt.show()


X = X_99[[ 'Marca','Modelo','Combustible','Gases  ralenti  co', 'Gases  ralenti  hc', 'Gases  ralenti  co2', 'Gases  ralenti  o2', 'Gases  crucero  co', 'Gases  crucero  hc', 
        'Gases  crucero  co2', 'Gases  crucero  o2']]


y = X_99[['Clasificacion nivel de contaminacion']]


print(X.shape, y.shape)

(9225, 11) (9225, 1)


from sklearn.model_selection import train_test_split
# separar los datos en train y eval
x_train, x_eval, y_train, y_eval = train_test_split(X, y, test_size=0.20, train_size=0.80, random_state=0)


from sklearn.svm import SVC
algoritmo=SVC(kernel='linear')


algoritmo.fit(x_train, y_train)

SVC(kernel='linear')


y_pred=algoritmo.predict(x_eval)


matriz_SVC=confusion_matrix(y_eval,y_pred)
print('Matriz de confusión: ')
print(matriz_SVC)

Matriz de confusión: 
[[ 232   10    0    0    0]
 [  12 1322    0    0    0]
 [   0    1   84    1    0]
 [   0    0    0  105    2]
 [   0    0    0    0   76]]


print('Precisión del clasificador en el conjunto de entrenamiento: {:.2f}'
     .format(algoritmo.score(x_train, y_train)))
print('Precisión del clasificador en el conjunto de prueba: {:.2f}'
     .format(algoritmo.score(x_eval, y_eval)))

Precisión del clasificador en el conjunto de entrenamiento: 0.98
Precisión del clasificador en el conjunto de prueba: 0.99


X = X_99[[ 'Marca','Modelo','Combustible','Gases  ralenti  co', 'Gases  ralenti  hc', 'Gases  ralenti  co2', 'Gases  ralenti  o2', 'Gases  crucero  co', 'Gases  crucero  hc', 
        'Gases  crucero  co2', 'Gases  crucero  o2']]


y = X_99[['Clasificacion nivel de contaminacion']]


from sklearn.model_selection import train_test_split
# separar los datos en train y eval
x_train, x_eval, y_train, y_eval = train_test_split(X, y, test_size=0.20, train_size=0.80, random_state=0)


from sklearn.neural_network import MLPClassifier

clf = MLPClassifier(solver='adam', alpha=0.0001,
                     hidden_layer_sizes=(10, 10, 10,10,10), random_state=0, max_iter=500, tol=0.0000000001)

clf.fit(x_train, y_train)
predictions=clf.predict(x_eval)


from sklearn.metrics import classification_report
print(classification_report(y_eval,predictions));

              precision    recall  f1-score   support

           1       0.84      0.96      0.90       242
           2       0.99      0.97      0.98      1334
           3       0.99      0.88      0.93        86
           4       0.94      0.94      0.94       107
           5       0.94      1.00      0.97        76

    accuracy                           0.96      1845
   macro avg       0.94      0.95      0.94      1845
weighted avg       0.97      0.96      0.96      1845


X = X_99[[ 'Marca','Modelo','Combustible','Gases  ralenti  co', 'Gases  ralenti  hc', 'Gases  ralenti  co2', 'Gases  ralenti  o2', 'Gases  crucero  co', 'Gases  crucero  hc', 
        'Gases  crucero  co2', 'Gases  crucero  o2']]


y = X_99[['Clasificacion nivel de contaminacion']]


from sklearn.model_selection import train_test_split
# separar los datos en train y eval
x_train, x_eval, y_train, y_eval = train_test_split(X, y, test_size=0.20, train_size=0.80, random_state=0)


import statsmodels.api as sm
import statsmodels.formula.api as smf
from statsmodels.stats.anova import anova_lm
from scipy import stats


# A la matriz de predictores se le tiene que añadir una columna de 1s para el intercept del modelo
x_train_reg = sm.add_constant(x_train, prepend=True)
modelo = sm.OLS(endog=y_train, exog=x_train_reg,)
modelo = modelo.fit()
print(modelo.summary())

                                     OLS Regression Results                                     
================================================================================================
Dep. Variable:     Clasificacion nivel de contaminacion   R-squared:                       0.697
Model:                                              OLS   Adj. R-squared:                  0.696
Method:                                   Least Squares   F-statistic:                     1537.
Date:                                  Mon, 07 Jun 2021   Prob (F-statistic):               0.00
Time:                                          19:54:22   Log-Likelihood:                -5264.6
No. Observations:                                  7380   AIC:                         1.055e+04
Df Residuals:                                      7368   BIC:                         1.064e+04
Df Model:                                            11                                         
Covariance Type:                              nonrobust                                         
=======================================================================================
                          coef    std err          t      P>|t|      [0.025      0.975]
---------------------------------------------------------------------------------------
const                  10.4454      1.459      7.160      0.000       7.586      13.305
Marca                  -0.0113      0.003     -3.554      0.000      -0.017      -0.005
Modelo                 -0.0036      0.001     -5.008      0.000      -0.005      -0.002
Combustible             0.1124      0.024      4.726      0.000       0.066       0.159
Gases  ralenti  co      0.1364      0.015      9.340      0.000       0.108       0.165
Gases  ralenti  hc      0.0004   2.07e-05     17.245      0.000       0.000       0.000
Gases  ralenti  co2    -0.0577      0.022     -2.604      0.009      -0.101      -0.014
Gases  ralenti  o2      0.0474      0.016      3.020      0.003       0.017       0.078
Gases  crucero  co      0.1347      0.014      9.808      0.000       0.108       0.162
Gases  crucero  hc      0.0003   2.32e-05     11.460      0.000       0.000       0.000
Gases  crucero  co2    -0.0634      0.021     -3.020      0.003      -0.105      -0.022
Gases  crucero  o2      0.0233      0.016      1.483      0.138      -0.007       0.054
==============================================================================
Omnibus:                      785.199   Durbin-Watson:                   1.996
Prob(Omnibus):                  0.000   Jarque-Bera (JB):             6818.606
Skew:                           0.078   Prob(JB):                         0.00
Kurtosis:                       7.706   Cond. No.                     5.11e+05
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 5.11e+05. This might indicate that there are
strong multicollinearity or other numerical problems.


# Diagnóstico errores (residuos) de las predicciones de entrenamiento
y_train = y_train.values
y_train=y_train.flatten()
prediccion_train = modelo.predict(exog = x_train_reg)
residuos_train   = prediccion_train - y_train


import seaborn as sns
fig, axes = plt.subplots(nrows=3, ncols=2, figsize=(9, 8))

axes[0, 0].scatter(y_train, prediccion_train, edgecolors=(0, 0, 0), alpha = 0.4)
axes[0, 0].plot([y_train.min(), y_train.max()], [y_train.min(), y_train.max()],
                'k--', color = 'black', lw=2)
axes[0, 0].set_title('Valor predicho vs valor real', fontsize = 10, fontweight = "bold")
axes[0, 0].set_xlabel('Real')
axes[0, 0].set_ylabel('Predicción')
axes[0, 0].tick_params(labelsize = 7)

axes[0, 1].scatter(list(range(len(y_train))), residuos_train,
                   edgecolors=(0, 0, 0), alpha = 0.4)
axes[0, 1].axhline(y = 0, linestyle = '--', color = 'black', lw=2)
axes[0, 1].set_title('Residuos del modelo', fontsize = 10, fontweight = "bold")
axes[0, 1].set_xlabel('id')
axes[0, 1].set_ylabel('Residuo')
axes[0, 1].tick_params(labelsize = 7)

sns.histplot(
    data    = residuos_train,
    stat    = "density",
    kde     = True,
    line_kws= {'linewidth': 1},
    color   = "firebrick",
    alpha   = 0.3,
    ax      = axes[1, 0]
)

axes[1, 0].set_title('Distribución residuos del modelo', fontsize = 10,
                     fontweight = "bold")
axes[1, 0].set_xlabel("Residuo")
axes[1, 0].tick_params(labelsize = 7)


sm.qqplot(
    residuos_train,
    fit   = True,
    line  = 'q',
    ax    = axes[1, 1], 
    color = 'firebrick',
    alpha = 0.4,
    lw    = 2
)
axes[1, 1].set_title('Q-Q residuos del modelo', fontsize = 10, fontweight = "bold")
axes[1, 1].tick_params(labelsize = 7)

axes[2, 0].scatter(prediccion_train, residuos_train,
                   edgecolors=(0, 0, 0), alpha = 0.4)
axes[2, 0].axhline(y = 0, linestyle = '--', color = 'black', lw=2)
axes[2, 0].set_title('Residuos del modelo vs predicción', fontsize = 10, fontweight = "bold")
axes[2, 0].set_xlabel('Predicción')
axes[2, 0].set_ylabel('Residuo')
axes[2, 0].tick_params(labelsize = 7)

# Se eliminan los axes vacíos
fig.delaxes(axes[2,1])

fig.tight_layout()
plt.subplots_adjust(top=0.9)
fig.suptitle('Diagnóstico residuos', fontsize = 12, fontweight = "bold");


# Normalidad de los residuos Shapiro-Wilk test
# ==============================================================================
shapiro_test = stats.shapiro(residuos_train);
shapiro_test

ShapiroResult(statistic=0.9231351613998413, pvalue=0.0)


# Normalidad de los residuos D'Agostino's K-squared test
# ==============================================================================
k2, p_value = stats.normaltest(residuos_train)
print(f"Estadítico= {k2}, p-value = {p_value}")

Estadítico= 785.1989262249446, p-value = 3.134870262040877e-171


# Error de test del modelo 
from sklearn.metrics import mean_squared_error
# ==============================================================================
x_eval = sm.add_constant(x_eval, prepend=True)
predicciones = modelo.predict(exog = x_eval)
rmse = mean_squared_error(
        y_true  = y_eval,
        y_pred  = predicciones,
        squared = False
       )
print("")
print(f"El error (rmse) de test es: {rmse}")

El error (rmse) de test es: 0.5175718718686321


prueba = pd.read_excel('prueba_RN.xlsx')
prueba


# KNN:
P_KNN = knn.predict(prueba)
P_KNN = pd.DataFrame(P_KNN)
P_KNN.to_excel('P_KNN.xlsx')


# ÁRBOL DECISIÓN:
P_DT = arbol2.predict(prueba)
P_DT = pd.DataFrame(P_DT)
P_DT.to_excel('P_DT.xlsx')


# MÁQUINA VECTOR SOPORTE:
P_SVM = algoritmo.predict(prueba)
P_SVM = pd.DataFrame(P_SVM)
P_SVM.to_excel('P_SVM.xlsx')


# RED NEURONAL:
P_NN = clf.predict(prueba)
P_NN = pd.DataFrame(P_NN)
P_NN.to_excel('P_NN.xlsx')


Xf = X_99[[ 'Gases  ralenti  hc','Gases  ralenti  o2', 'Gases  crucero  hc']]
yf = X_99[['Clasificacion nivel de contaminacion']]

# separar los datos en train y eval
x_train, x_eval, y_train, y_eval = train_test_split(Xf, yf, test_size=0.20, train_size=0.80, random_state=0)
arbol_f = DecisionTreeClassifier(criterion='gini', max_depth=4)

# Ajustando el modelo
arbol_f.fit(x_train, y_train)

print('Evaluación del modelo de Árboles de decisión con las 3 variables más importantes: ')

print('---------------------------------------------------------------------------------')
# precisión del modelo en datos de entrenamiento.
print("Precisión entrenamiento: {0: .2f}".format(
        arbol_f.score(x_train, y_train)))

# precisión del modelo en datos de evaluación.
print("Precisión evaluación: {0: .2f}".format(
        arbol_f.score(x_eval, y_eval)))
print('\n')
# Gráfico de importancia de los 3 predictores más importantes:
import matplotlib.pyplot as plt
from matplotlib import style
import seaborn as sns
style.use('ggplot') or plt.style.use('ggplot')

# visualizar importancia con el modelo 'arbol_f':
fig, ax = plt.subplots(figsize=(6, 3.84));
x = Xf.columns
y1 = arbol_f.feature_importances_ #importancia de cada variable predictora
sns.barplot(x=x, y=y1)
plt.title('Importancia de cada predictor con el modelo: "arbol_f"')
plt.show()

Evaluación del modelo de Árboles de decisión con las 3 variables más importantes: 
---------------------------------------------------------------------------------
Precisión entrenamiento:  0.88
Precisión evaluación:  0.87


from mlxtend.plotting import plot_decision_regions
# regiones de decisión en 2D con las variables más representativas del modelo final ("arbol2"):
X= pd.concat([X_99['Gases  ralenti  hc'],X_99['Gases  ralenti  o2']], axis=1)
y = X_99['Clasificacion nivel de contaminacion']

X2 = X.iloc[:,[1,0]].values # variable 1 = Gases ralenti hc ; variable 3 = Gases ralenti o2
y2 = y.iloc[:].values       # variable respuesta = Clasificacion nivel de contaminacion

arbol_f.fit(X2,y2)           # usamos el arbol2 resultante en el modelo final
fig, ax = plt.subplots(figsize=(10, 7))
plot_decision_regions(X2, y2, clf=arbol2, legend=2)
plt.xlabel('Gases  ralenti  hc')
plt.ylabel('Gases  ralenti  o2')
plt.title('Clasificación de gases ralenti hc y o2 con respecto al nivel de contaminación')
plt.show()

Number of Variables	25
Number of Rows	9226
Missing Cells	0
Missing Cells (%)	0.0%
Duplicate Rows	0
Duplicate Rows (%)	0.0%
Total Size in Memory	3.7 MB
Average Row Size in Memory	423.8 B

Numerical	19
DateTime	2
Categorical	4

Distinct Count	8335
Unique (%)	90.3%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	5305.1853
Minimum	0
Maximum	11969
Zeros	85
Zeros (%)	0.9%
Negatives	0
Negatives (%)	0.0%

Minimum	0
5-th Percentile	188
Q1	1701.75
Median	5182
Q3	8588.5
95-th Percentile	11273.75
Maximum	11969
Range	11969
IQR	6886.75

Mean	5305.1853
Standard Deviation	3716.859
Variance	1.3815e+07
Sum	4.8946e+07
Skewness	0.1383
Kurtosis	-1.3051
Coefficient of Variation	0.7006

Distinct Count	9214
Unique (%)	99.9%
Missing	0
Missing (%)	0.0%
Memory Size	72.2 KB
Minimum	2018-10-29 10:15:00
Maximum	2021-05-07 07:13:00

Mean	1.3014
Standard Deviation	0.4799
Variance	0.2303
Sum	12007
Skewness	1.1307
Kurtosis	-0.07679
Coefficient of Variation	0.3688

Distinct Count	6
Unique (%)	0.1%
Missing	0
Missing (%)	0.0%
Memory Size	645.9 KB

1st row	OTRA
2nd row	OTRA
3rd row	RENAULT
4th row	TOYOTA
5th row	OTRA

Count	61728
Lowercase Letter	0
Space Separator	0
Uppercase Letter	61728
Dash Punctuation	0
Decimal Number	0

Distinct Count	981
Unique (%)	10.6%
Missing	0
Missing (%)	0.0%
Memory Size	757.8 KB

Mean	19.0966
Standard Deviation	4.4992
Median	18
Minimum	7
Maximum	42

1st row	[VOLKSWAGEN] JETTA...
2nd row	[NISSAN] MARCH
3rd row	[RENAULT] SANDERO
4th row	[TOYOTA] COROLLA
5th row	[AUDI] A3

Count	132649
Lowercase Letter	131
Space Separator	18290
Uppercase Letter	132518
Dash Punctuation	125
Decimal Number	6388

Distinct Count	71
Unique (%)	0.8%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	2004.5066
Minimum	1900
Maximum	2020
Zeros	0
Zeros (%)	0.0%
Negatives	0
Negatives (%)	0.0%

Minimum	5.4
5-th Percentile	17.3
Q1	20.2
Median	20.4
Q3	23.1
95-th Percentile	25.5
Maximum	41.5
Range	36.1
IQR	2.9

Distinct Count	3474
Unique (%)	37.6%
Missing	0
Missing (%)	0.0%
Memory Size	72.2 KB
Minimum	1900-06-01 00:00:00
Maximum	2099-12-29 00:00:00

1st row	GASOLINA
2nd row	GASOLINA
3rd row	GASOLINA
4th row	GASOLINA
5th row	GASOLINA

Count	74414
Lowercase Letter	0
Space Separator	364
Uppercase Letter	74414
Dash Punctuation	176
Decimal Number	0

Distinct Count	277
Unique (%)	3.0%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	1742.9323
Minimum	0
Maximum	40000
Zeros	10
Zeros (%)	0.1%
Negatives	0
Negatives (%)	0.0%

Minimum	0
5-th Percentile	1000
Q1	1300
Median	1597
Q3	1975
95-th Percentile	3000
Maximum	40000
Range	40000
IQR	675

Distinct Count	7094
Unique (%)	76.9%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	160118.468
Minimum	0
Maximum	5.462e+06
Zeros	469
Zeros (%)	5.1%
Negatives	0
Negatives (%)	0.0%

Minimum	0
5-th Percentile	0
Q1	78912.75
Median	125800
Q3	193438.75
95-th Percentile	391470.25
Maximum	5.462e+06
Range	5.462e+06
IQR	114526

Distinct Count	208
Unique (%)	2.3%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	21.3565
Minimum	5.4
Maximum	41.5
Zeros	0
Zeros (%)	0.0%
Negatives	0
Negatives (%)	0.0%

Distinct Count	591
Unique (%)	6.4%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	56.5416
Minimum	30
Maximum	89.9
Zeros	0
Zeros (%)	0.0%
Negatives	0
Negatives (%)	0.0%

Minimum	30
5-th Percentile	36.7
Q1	46.8
Median	54.9
Q3	65.9
95-th Percentile	80.275
Maximum	89.9
Range	59.9
IQR	19.1

DATOS CDA LA CEJA¶

Preprocesamiento de datos:¶

EDA¶

Overview

Dataset Statistics

Variable Types

Variables

Numero fur

Quantile Statistics

Descriptive Statistics

Fecha inicio

Codigo resultado

Quantile Statistics

Descriptive Statistics

Marca

Length

Sample

Letter

Linea

Length

Sample

Letter

Modelo

Quantile Statistics

Descriptive Statistics

Fecha matricula

Combustible

Length

Sample

Letter

Cilindraje

Quantile Statistics

Descriptive Statistics

Kilometraje

Quantile Statistics

Descriptive Statistics

Gases temperatura ambiente

Quantile Statistics

Descriptive Statistics

Gases humedad relativa

Quantile Statistics

Descriptive Statistics

Gases convertidor catalitico

Length

Sample

Letter

Gases ralenti rpm

Quantile Statistics

Descriptive Statistics

Gases ralenti co

Quantile Statistics

Descriptive Statistics

Gases ralenti hc

Quantile Statistics

Descriptive Statistics

Gases ralenti co2

Quantile Statistics

Descriptive Statistics

Gases ralenti o2

Quantile Statistics

Descriptive Statistics

Gases crucero rpm

Quantile Statistics

Descriptive Statistics

Gases crucero co

Quantile Statistics

Descriptive Statistics

Gases crucero hc

Quantile Statistics

Descriptive Statistics

Gases crucero co2

Quantile Statistics

Descriptive Statistics

Gases crucero o2

Quantile Statistics

Descriptive Statistics

Nivel de contaminacion

Quantile Statistics

Descriptive Statistics

Clasificacion nivel de contaminacion

Count	22584
Lowercase Letter	16938
Space Separator	0
Uppercase Letter	5646
Dash Punctuation	0
Decimal Number	0

Distinct Count	636
Unique (%)	6.9%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	795.6508
Minimum	401
Maximum	1095
Zeros	0
Zeros (%)	0.0%
Negatives	0
Negatives (%)	0.0%

Distinct Count	663
Unique (%)	7.2%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	0.6278
Minimum	0
Maximum	13.1
Zeros	2509
Zeros (%)	27.2%
Negatives	0
Negatives (%)	0.0%

Distinct Count	898
Unique (%)	9.7%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	166.5987
Minimum	0
Maximum	15876
Zeros	18
Zeros (%)	0.2%
Negatives	0
Negatives (%)	0.0%

Distinct Count	222
Unique (%)	2.4%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	13.2371
Minimum	2.3
Maximum	15.5
Zeros	0
Zeros (%)	0.0%
Negatives	0
Negatives (%)	0.0%

Minimum	2.3
5-th Percentile	10.2
Q1	12.7
Median	13.7
Q3	14.3
95-th Percentile	14.7
Maximum	15.5
Range	13.2
IQR	1.6

Distinct Count	585
Unique (%)	6.3%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	1.3049
Minimum	0
Maximum	17.2
Zeros	892
Zeros (%)	9.7%
Negatives	0
Negatives (%)	0.0%

Distinct Count	478
Unique (%)	5.2%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	2495.9756
Minimum	2253
Maximum	2746
Zeros	0
Zeros (%)	0.0%
Negatives	0
Negatives (%)	0.0%

Distinct Count	715
Unique (%)	7.8%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	0.7527
Minimum	0
Maximum	13.84
Zeros	2476
Zeros (%)	26.8%
Negatives	0
Negatives (%)	0.0%

Distinct Count	712
Unique (%)	7.7%
Missing	0
Missing (%)	0.0%
Infinite	0
Infinite (%)	0.0%
Memory Size	144.2 KB
Mean	120.7846
Minimum	0
Maximum	11436
Zeros	8
Zeros (%)	0.1%
Negatives	0
Negatives (%)	0.0%